Predictive no-reference assessment of video quality
作者：
Highlights：
• A generic NR method for real-time quality assessment of streaming video is proposed.
• It uses supervised learning techniques for achieving high accuracy and adaptivity.
• It is evaluated in a broad set of videos streamed over lossy networks.
• To prove its generality, nine representative supervised learning models are employed.
• Our method obtains a 97% correlation to the Video Quality Metric.
摘要
•A generic NR method for real-time quality assessment of streaming video is proposed.•It uses supervised learning techniques for achieving high accuracy and adaptivity.•It is evaluated in a broad set of videos streamed over lossy networks.•To prove its generality, nine representative supervised learning models are employed.•Our method obtains a 97% correlation to the Video Quality Metric.
论文关键词：Quality of experience,No-Reference Video quality assessment,Supervised machine learning
论文评审过程：Received 11 August 2016, Revised 3 November 2016, Accepted 4 December 2016, Available online 8 December 2016, Version of Record 2 January 2017.
论文官网地址：https://doi.org/10.1016/j.image.2016.12.001
